Llama Guard 3 1B is an open-weight language model that classifies text for safety risks across categories such as violence, privacy, hate, self-harm, and sexual content. Developers can run it locally or deploy it in AI safety and content-moderation pipelines.
Llama Guard 3 1B sits in PulseGate's Foundation models & chat category. It focuses on detecting and classifying unsafe content in prompts and model responses. It is built as an open-source project for AI developers and safety engineers. The project is open source (MIT). It runs on the web, the command line, and API, and it can be self-hosted.
It is developed by alpindale, and it first shipped in 2023. Development happens publicly on GitHub with 18.6k stars. Among its 7 catalogued features are safety classification, content moderation, and prompt screening.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do